Genesys
未认领Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.
安装
claude mcp add genesys -- python -m genesys_memory更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
13 个工具中显示 13 个
文档中列出的工具 (13)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
delete_memory
Permanently delete a memory
list_core_memories
List core memories, optionally filtered by category
memory_amend
Record a correction: creates a new memory that supersedes an existing one. The old memory is kept (decayed in recall), not deleted.
memory_explain
Explain a memory's score. Includes a scoremodel block (formula + live per-force breakdown + staleness note) and removalimpact.
memory_recall
Recall memories by natural language query (vector + keyword + graph spreading activation). Supports verbosity: "concise" for lightweight payloads.
memory_search
Filtered vector search by status, category, date (since), last-active date (activesince), or entity. Pass an empty query to enumerate by recency instead (no embedder needed) — with since/activesince this answers "what's new since I last looked" without knowing what to query for.
memory_stats
Get memory system statistics
memory_store
Store a new memory. Use related for writer-specified typed edges ({id, type}); relatedto is legacy and always creates causedby. Optional category. May return possibleconflicts (heuristic hints).
memory_traverse
Walk the causal graph from a node. Returns reachable nodes and the edges of the induced subgraph (source/target/type/weight/createdby) — a superset of the BFS tree, so paths can be reconstructed. Honors edgetypes.
pin_memory
Pin a memory so it's never forgotten
promote_to_org
Promote a private memory to org visibility
set_core_preferences
Set user preferences for core memory categories
unpin_memory
Unpin a previously pinned memory